Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    minimising

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ON
    0.84
    Sap
    0.79
     Valve
    0.77
    按照
    0.77
     எம்
    0.76
    OUT
    0.75
    AN
    0.73
     Neptune
    0.73
     克
    0.72
    upload
    0.72
    POSITIVE LOGITS
     shrink
    0.79
     lograr
    0.79
     decreases
    0.73
     shrinks
    0.73
     minimising
    0.71
     nami
    0.69
     mínimos
    0.67
     hermit
    0.67
     shrank
    0.67
    ේව
    0.67
    Act Density 0.004%

    No Known Activations